{"id":"https://openalex.org/W2025344720","doi":"https://doi.org/10.1155/2007/27616","title":"Detection and Separation of Speech Events in Meeting Recordings Using a Microphone Array","display_name":"Detection and Separation of Speech Events in Meeting Recordings Using a Microphone Array","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2025344720","doi":"https://doi.org/10.1155/2007/27616","mag":"2025344720"},"language":"en","primary_location":{"id":"doi:10.1155/2007/27616","doi":"https://doi.org/10.1155/2007/27616","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2007/27616","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-c","jufo-1","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1155/2007/27616","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112430812","display_name":"Futoshi Asano","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Futoshi Asano","raw_affiliation_strings":["Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Umezono, Tsukuba, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Umezono, Tsukuba, Japan#TAB#","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016899140","display_name":"Kiyoshi Yamamoto","orcid":"https://orcid.org/0000-0001-9351-5174","observed_orcids":["https://orcid.org/0000-0001-9351-5174"]},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kiyoshi Yamamoto","raw_affiliation_strings":["Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Umezono, Tsukuba, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Umezono, Tsukuba, Japan#TAB#","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006504365","display_name":"Jun Ogata","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Ogata","raw_affiliation_strings":["Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Umezono, Tsukuba, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Umezono, Tsukuba, Japan#TAB#","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110083878","display_name":"Miichi Yamada","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miichi Yamada","raw_affiliation_strings":["Advanced Media Inc., Toshima-Ku, Tokyo, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Media Inc., Toshima-Ku, Tokyo, Japan#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103507424","display_name":"Masami Nakamura","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masami Nakamura","raw_affiliation_strings":["Advanced Media Inc., Toshima-Ku, Tokyo, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Media Inc., Toshima-Ku, Tokyo, Japan#TAB#","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1890,"currency":"USD","value_usd":1890},"apc_paid":{"value":1890,"currency":"USD","value_usd":1890},"fwci":3.8721,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93402907,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"2007","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.019300000742077827,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-event-detection","display_name":"speech event detection","score":0.9309999942779541},{"id":"https://openalex.org/keywords/overlapping-speech","display_name":"overlapping speech","score":0.8370000123977661},{"id":"https://openalex.org/keywords/microphone-array","display_name":"microphone array","score":0.7089999914169312},{"id":"https://openalex.org/keywords/adaptive-beamforming","display_name":"adaptive beamforming","score":0.9990000128746033},{"id":"https://openalex.org/keywords/microphone-calibration","display_name":"microphone calibration","score":0.7960000038146973},{"id":"https://openalex.org/keywords/meeting-recordings","display_name":"meeting recordings","score":0.9039999842643738},{"id":"https://openalex.org/keywords/spontaneous-speech","display_name":"spontaneous speech","score":0.9549999833106995},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.875}],"concepts":[{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.7209303975105286},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6802072525024414},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.60458904504776},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5619093775749207},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.495900958776474},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4247360825538635},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39160656929016113},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15914210677146912},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.07201167941093445},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.06007501482963562}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1155/2007/27616","doi":"https://doi.org/10.1155/2007/27616","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2007/27616","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-c","jufo-1","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4e05781ca2fb4ae792bec865a6b08d16","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/4e05781ca2fb4ae792bec865a6b08d16","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2007, Iss 1, p 027616 (2007)","raw_type":"article"},{"id":"pmh:oai:doaj.org/article:9659404b432f4266855907287f25bb81","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/9659404b432f4266855907287f25bb81","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2007 (2007)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1155/2007/27616","doi":"https://doi.org/10.1155/2007/27616","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2007/27616","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-c","jufo-1","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W102337716","https://openalex.org/W127001119","https://openalex.org/W1651870529","https://openalex.org/W1963844140","https://openalex.org/W2016100027","https://openalex.org/W2071795835","https://openalex.org/W2099984896","https://openalex.org/W2100969003","https://openalex.org/W2108357193","https://openalex.org/W2113638573","https://openalex.org/W2116623987","https://openalex.org/W2132056833","https://openalex.org/W2146871184","https://openalex.org/W2162445491","https://openalex.org/W2164427415","https://openalex.org/W2172218156"],"related_works":["https://openalex.org/W2077696091","https://openalex.org/W127001119","https://openalex.org/W2116623987","https://openalex.org/W2401696961","https://openalex.org/W2785864403","https://openalex.org/W2159284737","https://openalex.org/W2071795835","https://openalex.org/W2889664202","https://openalex.org/W2147166770","https://openalex.org/W1996837089"],"abstract_inverted_index":{"When":[0],"applying":[1],"automatic":[2],"speech":[3,23,34],"recognition":[4],"(ASR)":[5],"to":[6],"meeting":[7,68,88],"recordings":[8,69],"including":[9,62],"spontaneous":[10],"speech,":[11],"the":[12,20,32,54,58,72,80],"performance":[13,78],"of":[14,22,30,48,60,74,79],"ASR":[15,85],"is":[16,43,51,65,82],"greatly":[17],"reduced":[18],"by":[19,36],"overlap":[21],"events.":[24],"In":[25],"this":[26,49],"paper,":[27],"a":[28],"method":[29,50],"separating":[31],"overlapping":[33],"events":[35],"using":[37,86],"an":[38],"adaptive":[39],"beamforming":[40],"(ABF)":[41],"framework":[42],"proposed.":[44],"The":[45,77],"main":[46],"feature":[47],"that":[52],"all":[53],"information":[55],"necessary":[56],"for":[57],"adaptation":[59],"ABF,":[61],"microphone":[63],"calibration,":[64],"obtained":[66],"from":[67],"based":[70],"on":[71],"results":[73],"speech-event":[75],"detection.":[76],"separation":[81],"evaluated":[83],"via":[84],"real":[87],"recordings.":[89]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2016-06-24T00:00:00"}